Skip to content

Visual review

Step

Does
looks at frames across each episode and records a grade and a note per scene the metrics may have misjudged.
Passes when
every rendered scene's contact sheet has been looked at and visual_review.json covers every scene you have an opinion on.

Inputs. A collected run dir from render-and-grade. Tools. ffmpeg, collect.py.

  1. Open every media/SCENE_sheet.jpg (12 frames across the episode). Look for jitter, explosions, interpenetration, launched or floating bodies, and bodies vanishing into geometry.
  2. When a sheet looks off, pull single frames:
    ffmpeg -ss 7.5 -i "$RUN/out/SCENE/clip_raw.mp4" -frames:v 1 frame.jpg
    
  3. Before calling a body lost, find it in the poses: a fixed camera cannot see into a bin behind a deck, and the example’s own check may count it. Compare doubtful metrics with another solver on the same scene.
  4. Write $RUN/visual_review.json:
    {"crane_wrecking_ball": {"grade": "ok", "note": "the ball knocks the building down as scripted; nothing launches or sinks"}}
    
    then run collect.py and build_gallery.py again.

Rules. A visual note can raise a grade; it never hides an automatic unstable or failed. Say what you saw, at what time, in which part of the frame.

Outputs. visual_review.json and a regenerated results.json and gallery.

Source: agents/steps/visual-review/README.md, the copy agents read.